skills.rest
LogauaEngstrom
LogauaEngstromCOMMUNITY
Explore all skills by this author →
GitHub

generate-image

Generate or edit images from prompts using OpenRouter AI models.

18|1|Updated Dec 27, 2025
Search Tags:#editing#image#ai#visuals#openrouter#generate#prompt
One-click install
npx skills add https://github.com/LogauaEngstrom/claude-scientific-skills --skill generate-image-logauaengstrom
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: generate-image
Source: https://github.com/LogauaEngstrom/claude-scientific-skills/tree/main/scientific-skills/generate-image
Command: npx skills add https://github.com/LogauaEngstrom/claude-scientific-skills --skill generate-image-logauaengstrom

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

This skill enables quick generation and editing of high-quality images using AI models, reducing turnaround time for visual assets and concept exploration.

Core Features & Use Cases

  • Generate photorealistic images from descriptive prompts and model choices.
  • Edit existing images with natural-language instructions and input images.
  • Switch between OpenRouter models (Gemini 3 Pro Image Preview, FLUX.2 Pro) to balance quality and speed.
  • Use in creative workflows for marketing visuals, research illustrations, presentations, and concept art.

Quick Start

Use the script to generate or edit an image by providing a descriptive prompt.

Frequently Asked Questions about generate-image

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI images from text prompts?▼

To generate AI images from text prompts, provide a descriptive prompt and select an OpenRouter model. The skill transforms your text into visual outputs and saves the resulting image directly to your filesystem.

Can I edit existing images using natural language instructions?▼

Yes, you can edit existing images by providing an optional input image alongside natural-language instructions. The AI model processes your prompt to modify the input image and saves the edited visual result.

Do I need an OpenRouter API key to generate visuals?▼

Yes, you need an OpenRouter API key to generate visuals. The skill handles API key provision to access models like Gemini 3 Pro Image Preview and FLUX.2 Pro for transforming prompts into visual outputs.

What is the best way to create concept art for marketing visuals?▼

The best way to create concept art for marketing visuals is using OpenRouter models to transform descriptive prompts into photorealistic or stylized outputs, reducing turnaround time for visual asset exploration.

Does this image generation skill support both photorealistic and stylized styles?▼

Yes, the image generation skill supports both photorealistic and stylized styles. By switching between OpenRouter models like FLUX.2 Pro and Gemini 3 Pro Image Preview, you can balance output quality and speed.

Related Skills

Explore More Design & Creative Skills→
fuzzy-dynamicsfuzzy-dynamics
1

generate-image

Generate and edit images via OpenRouter AI models with prompts and optional input images.

Official
Intermediate
dralkhdralkh
74

generate-image

Generate and edit images from text prompts and reference images via OpenRouter.

Community
Intermediate
GroundMountCompanyGroundMountCompany

ai-image-generation

Automate AI image generation via Replicate API with model selection and iterative refinement.

Community
Intermediate
qq5855144qq5855144
23

minimax-text-to-image

Generate images from text prompts using the MiniSearch API.

Community
Advanced